colab上更换python版本或者换成tensorflow1.x版本

cd /content/drive/MyDrive/

# 安装python，可选择自己需要的版本
!apt-get install python3.6
!ls /usr/bin/| grep python
# 卸载掉当前的pip
!python -m pip uninstall pip

# 将下载的python3.6软连接到python
%%bash
export py=`which python`
sudo rm $py
export py36=`which python3.6`
sudo ln -s $py36 $py

# 重新安装pip
!sudo apt-get install python3.6-distutils
!wget https://bootstrap.pypa.io/pip/3.6/get-pip.py
!python get-pip.py

!pip install tensorflow-gpu==1.15.0
!python -V
!pip -V

import tensorflow as tf
print(tf.__version__)

import tensorflow as tf

# 这里使用Numpy生成模拟数据集
from numpy.random import RandomState

tf.compat.v1.disable_eager_execution()

# 定义训练数据batch的大小
batch_size = 8

# 定义神经网络的参数
w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1))
w2 = tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1))

# 在shape的一个维度上使用None方便使用不同的batch大小。
x = tf.placeholder(tf.float32, shape=(None, 2), name='x-input')
y_ = tf.placeholder(tf.float32, shape=(None, 1), name='y-input')

# 定义神经网络前向传播过程
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)

# 定义损失函数和反向传播算法
y = tf.sigmoid(y)
cross_entropy = -tf.reduce_mean(
    y_ * tf.log(tf.clip_by_value(y, 1e-10, 1.0))
    + (1 - y) * tf.log(tf.clip_by_value(1 - y, 1e-10, 1.0))
)
train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)

# 通过随机数生成一个模拟数据集
rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size, 2)

# 假设0为负样本，1为正样本。x1+x2<1 为正样本
Y = [[int(x1 + x2 < 1)] for (x1, x2) in X]

# 创建会话运行Tensorflow程序
with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    # 初始化变量
    sess.run(init_op)

    print(sess.run(w1))
    print(sess.run(w2))

    # 设定训练的轮数
    STEPS = 5000
    for i in range(STEPS):
        # 每次选取batch_size个样本进行训练
        start = (i * batch_size) % dataset_size
        end = min(start + batch_size, dataset_size)

        # 通过选取的样本训练神经网络并更新参数
        sess.run(train_step,
                 feed_dict={x: X[start:end], y_: Y[start:end]})
        if i % 1000 == 0:
            # 每隔一段时间计算所有数据的交叉熵
            total_cross_entropy = sess.run(
                cross_entropy, feed_dict={x: X, y_: Y}
            )
            print("After %d train steps,cross entropy on all data is %g" % (i, total_cross_entropy))

    print(sess.run(w1))
    print(sess.run(w2))